DataMin seminars
2017 2016   2015   2014   2013   2012   2011   2010   2009   2008   2007
2011
WINTER BREAK

22.12.2011
Wednesday
Dimensionality reduction and extrapolation
Presenter: Róbert Terkál
Links:
  • Y. Bengio, J-F. Paiement, P. Vincent, O. Delalleau, N. Le Roux, M. Ouimet (2004) Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering (NIPS, 2003) PDF.

16:00, Math207

15.12.2011
Wednesday
Spectral dimensionality reduction via Maximum Entropy
Presenter: Lehel Csató
There are several recent documents, we will read the paper.
Links:
  • Neil D. Lawrence (2011) Spectral Dimensionality Reduction via Maximum Entropy (AISTATS) PDF.
  • Neil D. Lawrence (2011) (slides)Spectral Dimensionality Reduction via Maximum Entropy (AISTATS) PDF.
  • VIDEOLECTURES TALK LINK TO THE TALK.

16:00, Math207

07.12.2011
Wednesday
PILCO: a model-based and data-efficient approach to policy search
Presenter: Hunor Jakab
Links:
  • Marc Peter Deisenroth, Carl Edward Rasmussen (2011) PILCO: a model-based and data-efficient approach to policy search (ICML) PDF.

16:00, Math207

30.11.2011
Wednesday
Bayesian Optimal Design
Presenter: Lehel Csató
Links:
  • Matthias Seeger, Florian Steinke, Koji Tsuda (2007) Bayesian Inference and Optimal Design in the Sparse Linear Model (AISTATS) PDF.

16:00, Math207

23.11.2011
Wednesday
Conditional random fields, tutorial (II)
Presenter: Zalán Bodó
Links:
Continuing the discussion of the inference algorithms for the CRF parameters
16:00, Math207

16.11.2011
Wednesday
Conditional random fields, tutorial
Presenter: Zalán Bodó
Links:
  • Roman Klinger and Katrin Tomanek (2007) Classical Probabilistic Models and Conditional Random Fields PDF.

14:30, Math207

11.11.'11
Friday
Online learning reloaded (discussing Colt papers, as in 25.08.2011)
Presenter: Hunor Jakab

11:11, Math207

02.11.2011
Wednesday
Data visualization
Presenter: Botond Bócsi
Links:
  • L. ved der Maaten, G. Hinton (2008) Visualizing Data using t-SNE PDF.

16:00, Math207

SUMMER BREAK

25.08.2011
Thursday
Online learning (COLT 2011 papers)
Presenter: Hunor Jakab
Links:
  • Alexander R.,Karthik S., Ambuj T: Online Learning: Beyond Regret PDF.
  • Abernethy J., Bartlett P., Hazan E.: Blackwell Approachability and No-Regret Learning are Equivalent PDF.

14:00, Math207

14.02.2011
Monday
Automatic basis function selection for dynamic programming
Presenter: Lehel Csató
Links:
  • Keller P.W, Mannor S, Precup D: Automatic basis function construction for approximate dynamic programming and reinforcement learning PDF.

14:00, Math207

07.02.2011
Monday
Least squares policy iteration
Presenter: Hunor Jakab
Links:
  • Lagoudakis, Michail G. and Parr, Ronald: Least-squares policy iteration (Journal of Machine Learning, 2003) PDF.
  • Lagoudakis, Michail G. and Parr, Ronald: Model-free Least-squares policy iteration(NIPS, 2001) PDF.

14:00, Math207

31.01.2011
Monday
Geodesic Gaussian Kernels for Value Function Approximation
Presenter: Hunor Jakab
Links:
  • M. Sugiyama, H. Hachiya, C. Towell, S. Vijayakumar: Geodesic Gaussian Kernels for Value Function Approximation (Autonomous Robotics) PDF.
  • S. Wu, S.-I. Amari: Improving Support Vector Machine Classifiers by Modifying Kernel Functions (Neural Networks, 12/6, pp. 783-789, 1999)
  • P. Williams, S. Li, J. Feng, S. Wu: A Geometrical Method to Improve Performance of the Support Vector Machine (IEEE Tr. on Neural Networks, 18/3 pp. 942--947, 2007)

14:00, Math207

24.01.2011
Monday
Bayesian Estimation and Smoothing Splines
Presenter: Lehel Csató
Links:
  • George S. Kimeldorf and Grace Wahba: A Correspondence Between Bayesian Estimation on Stochastic Processes and Smoothing by Splines (The Annals of Mathematical Statistics, 1970, 41/2 pp. 495--502) PDF.

14:00, Math207